Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 36149
    Prev
    Next
    INDEX
    Explanations

    technical details and parameters related to astrophysics and stellar characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    solar mass $M_\odot$

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arXiv
    -0.59
     researchers
    -0.41
     arXiv
    -0.40
     chercheurs
    -0.38
     EconPapers
    -0.36
     economists
    -0.35
    Скачать
    -0.34
    arxiv
    -0.34
     scholars
    -0.33
    enosis
    -0.31
    POSITIVE LOGITS
    aarrggbb
    0.64
    postIndex
    0.63
    MessageOf
    0.62
    󠁣
    0.58
    EDEFAULT
    0.56
    hoeddwyd
    0.55
    TagHelper
    0.55
    UpdateCommand
    0.54
    ReusableCell
    0.54
    #+#
    0.54
    Activations Density 0.281%

    No Known Activations